© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2311
    Prev
    Next
    INDEX
    Explanations

    format or formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ar
    3.26
    ceptron
    3.09
    ות
    3.07
    ্ধ্য
    3.00
    al
    2.98
    क
    2.96
    ುವ
    2.95
    өк
    2.93
    ма
    2.92
    ৃঙ্খলা
    2.84
    POSITIVE LOGITS
    __(/*!
    3.83
    tes
    3.51
    tf
    3.26
    nl
    3.16
    tl
    3.16
    브
    3.07
    tm
    3.05
    逅
    3.04
    nm
    3.02
    ोत्तम
    2.95
    Activations Density 0.114%

    No Known Activations